Advanced Algorithms for Treatment Management Applications (AATMA)
K212218Elekta Solutions AB · cleared 2021-10-25 · product code QKB · Radiology
Premarket evidence — what FDA accepted
source quote (p.3)
“AATMA™ is a medical image processing library intended to produce derived data sets for use as input into radiation therapy treatment planning systems or other intermediate pre-treatment-planning applications. AATMA™ does not provide a user interface and is designed to be accessed through its application programming interface (API) by other devices. The data sets created by AATMA™ must be reviewed and validated by a qualified healthcare professional prior to clinical use.”
source quote (p.4)
“The auto-segmentation algorithm in AATMA™ is based on machine-learning convolutional neural networks and includes pre-trained models that will be used to automatically segment image sets.”
source quote (p.4)
“The available models have been pre-trained on specific datasets that exhibit similar characteristics (e.g., body site and imaging modality).”
Validation studies (2)
Retrospective clinical
n=13 images
endpoints: DICE coefficient
standards: FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.", CFR 21 Part 820, DICOM standard
Retrospective clinical
n=20 images
endpoints: DICE coefficient
standards: FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices.", CFR 21 Part 820, DICOM standard
Reported performance (2 observations)
source quote (p.6)
“A different set of six(6) patient CT image sets with expert contours were chosen for verification and the average DICE coefficient over all structures was determined to be 0.84 which met the defined acceptance criteria.”
source quote (p.6)
“A different set of five (5) patient CT image sets with expert contours were chosen for verification and the average DICE coefficient over all structures was determined to be 0.93 which met the defined acceptance criteria.”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).